More than Words: Syntactic Packaging and Implicit Sentiment

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, pages 503–511, Boulder, Colorado, June 2009. c⃝2009 Association for Computational Linguistics More than Words: Syntactic Packaging and Implicit Sentiment Stephan Greene∗ ATG, Inc. 1111 19th St, NW Suite 600 Washington, DC 20036 sgreene@atg.com Philip Resnik Linguistics / UMIACS CLIP Laboratory University of Maryland College Park, MD 20742 resnik@umiacs.umd.edu Abstract Work on sentiment analysis often focuses on the words and phrases that people use in overtly opinionated text. In this paper, we in- troduce a new approach to the problem that focuses not on lexical indicators, but on the syntactic “packaging” of ideas, which is well suited to investigating the identification of im- plicit sentiment, or perspective. We establish a strong predictive connection between linguis- tically well motivated features and implicit sentiment, and then show how computational approximations of these features can be used to improve on existing state-of-the-art senti- ment classification results. 1 Introduction As Pang and Lee (2008) observe, the last several years have seen a “land rush” in research on senti- ment analysis and opinion mining, with a frequent emphasis on the identification of opinions in evalua- tive text such as movie or product reviews. How- ever, sentiment also may be carried implicitly by statements that are not only non-evaluative, but not even visibly subjective. Consider, for example, the following two descriptions of the same (invented) event: 1(a) On November 25, a soldier veered his jeep into a crowded market and killed three civilians. (b) On November 25, a soldier’s jeep veered into a crowded market, causing three civilian deaths. ∗This work was done while the first author was a student in the Department of Linguistics, University of Maryland. Both descriptions appear on the surface to be objec- tive statements, and they use nearly the same words. Lexically, the sentences’ first clauses differ only in the difference between ’s and his to express the rela- tionship between the soldier and the jeep, and in the second clauses both kill and death are terms with negative connotations, at least according to the Gen- eral Inquirer lexicon (Stone, 1966). Yet the descrip- tions clearly differ in the feelings they evoke: if the soldier were being tried for his role in what hap- pened on November 25, surely the prosecutor would be more likely to say (1a) to the jury, and the defense attorney (1b), rather than the reverse.1 Why, then, should a description like (1a) be per- ceived as less sympathetic to the soldier than (1b)? If the difference is not in the words, it must be in the way they are put together; that is, the structure of the sentence. In Section 2, we offer a specific hy- pothesis about the connection between structure and implicit sentiment: we suggest that the relationship is mediated by a set of “grammatically relevant” se- mantic properties well known to be important cross- linguistically in characterizing the interface between syntax and lexical semantics. In Section 3, we val- …

Content truncated to 500 words